Interdisciplinary Sciences: Computational Life Sciences最新文献

{"title":"Deep3D-DTA: A Tri-Modal Deep Learning Framework for Binding Affinity Prediction Leveraging 3D Structural Representations of Drugs and Targets.","authors":"Han Zhou, Xiumin Shi, Lu Wang","doi":"10.1007/s12539-026-00839-2","DOIUrl":"https://doi.org/10.1007/s12539-026-00839-2","url":null,"abstract":"<p><p>Predicting drug-target affinity (DTA) plays a pivotal role in drug discovery and repurposing. While existing computational approaches predominantly rely on 1D sequences or 2D structural data, they often fail to fully capture the intricate nature of molecular interactions. To address this limitation, we propose Deep3D-DTA, a novel tri-modal deep learning framework that integrates 1D sequence semantics, 2D graph topology, and 3D spatial geometry complementary representations for both drugs and target proteins. The proposed architecture offers three key advancements: First, it employs a pre-trained protein language model to encode amino acid sequences, effectively capturing long-range sequential dependencies. Second, it constructs precise 3D structural representations by computing interatomic distances and bond angles, enabling accurate modeling of the spatial conformations of both proteins and compounds. Third, it leverages a hybrid feature extraction module that combines graph neural networks with multi-head attention mechanisms to learn hierarchical structural patterns. Extensive experiments on three widely used benchmark datasets (Davis, KIBA, and Metz) demonstrate that Deep3D-DTA significantly outperforms state-of-the-art methods in DTA prediction. These results highlight its potential as a robust and reliable computational tool for accelerating drug discovery and reducing development costs through more accurate affinity prediction.</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148251488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ST-LDAW: A Topic-Model and Damped Weighted Least-Squares Method for Integrative Deconvolution of Single-Cell and Spatial Transcriptomics.","authors":"Xiaoyang Wang, Li C Xia, Huiling Liu, Chunxia Du, Lulu Chen, Zhimin Li, Yang Du, Yujia Li, Dongmei Ai","doi":"10.1007/s12539-026-00850-7","DOIUrl":"https://doi.org/10.1007/s12539-026-00850-7","url":null,"abstract":"<p><p>Integrating single-cell RNA sequencing (scRNA-seq) with spatial transcriptomics (ST) enables the projection of cell-type-resolved transcriptional programs onto tissue architecture. However, existing integration methods are often unstable because spot-level inference is performed directly in high-dimensional gene space, where extreme sparsity, measurement noise, and strong multicollinearity among marker genes amplify the estimation variance. As a result, inferred cell type proportions may be dominated by a small subset of genes, making them highly sensitive to noise and systematically distorting rare or low-abundance cell types. Here, we present ST-LDAW, which is a computational framework explicitly designed to address these challenges. ST-LDAW combines probabilistic topic modeling with damped weighted least squares optimization to enhance robustness at both the representation and inference levels. Topic-based modeling reduces dimensionality and mitigates gene-level noise by capturing coherent transcriptional programs, whereas damped weighting constrains the influence of unstable or low-confidence features, preventing variance inflation and overfitting during deconvolution. Benchmarking of simulated spatial mixtures demonstrated that ST-LDAW achieved a recall rate of 94% and an accuracy of 80%, surpassing existing regression-based and mapping-based methods in terms of sensitivity and precision. These results highlight ST-LDAW's ability to reliably identify cell types in complex, sparse datasets and its robust performance in handling rare or low-abundance cell types. Application to breast cancer ST data further reveals the subtype-specific cellular composition, functional heterogeneity, intercellular communication patterns, and key epithelial hub genes.</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148204823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MVFAN-Kcr: A Multi-View Feature Fusion and Attention-Based Network for Lysine Crotonylation Site Identification.","authors":"Yun Zuo, Li Zhou, Wenjie Gong, Qiao Ning, Xiangrong Liu, Sisi Yuan, Zhaohong Deng","doi":"10.1007/s12539-026-00846-3","DOIUrl":"https://doi.org/10.1007/s12539-026-00846-3","url":null,"abstract":"<p><p>Lysine crotonylation (Kcr), as an emerging post-translational modification, plays a crucial role in core life activities such as chromatin dynamics and gene expression. To address the current limitations of Kcr site detection techniques, including high experimental costs, complex procedures, and high false-positive rates, as well as the poor generalization performance of existing computational models caused by limited training data and class imbalance, this study proposes an innovative intelligent recognition framework named MVFAN-Kcr. The system integrates multi-view feature fusion and attention mechanisms to synergistically enhance the prediction accuracy and robustness of Kcr site identification. Physicochemical property features are combined with global sequence semantic information derived from the ESM-2 protein language model to construct a fused feature representation that captures both local physicochemical information and global contextual information. To optimize computational efficiency, feature selection is performed using analysis of variance. To effectively address the problem of imbalanced data distribution, a stratified undersampling strategy based on the chi-square test is developed. In addition, a convolutional neural network combined with attention is designed to efficiently extract local sequence patterns and enhance the representation of key features. Under a rigorous evaluation framework based on five-fold cross-validation and an independent test set, MVFAN-Kcr demonstrates excellent predictive performance. The method significantly outperforms baseline approaches in terms of accuracy, achieving an ACC value of 79.18%, while the area under the ROC curve reaches 0.8618. SHAP analysis and gradient-based analysis reveal a strong dependence on pKa-related properties, charge characteristics, and locally enriched small side-chain residues, and indicate that the model can nonlinearly integrate high-order sequence semantic information for effective identification of Kcr sites. Overall, MVFAN-Kcr combines data balancing strategies, multi-view feature fusion, and attention mechanisms to achieve high accuracy, robustness, and interpretability, providing an effective tool for protein Kcr site prediction. The data and code are available on https://github.com/Lilyjoys/MVFAN-Kcr , and a free web platform is provided at http://www.mvfan-kcr.com .</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148149816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MeDiCNet: Integrating Multi-scale Dynamic Convolution and Enhanced Position-Aware Transformer for DNA Methylation Site Prediction.","authors":"An Gong, Yuyang Zhan, Lekai Zhang, Anxuan Jia, Bing Yu, Yong Liu, Shuhui Wu","doi":"10.1007/s12539-026-00836-5","DOIUrl":"https://doi.org/10.1007/s12539-026-00836-5","url":null,"abstract":"<p><p>DNA methylation is a covalent modification of cytosine and adenine bases that regulates gene expression and underlies diverse biological processes and diseases. Existing computational methods often rely on fixed-scale feature extraction or static positional encodings, limiting their ability to model both fine-grained sequence motifs and long-range dependencies across multiple methylation chemistries. We present MeDiCNet, a unified deep-learning framework that combines multi-scale dynamic convolution with enhanced positional attention to predict N6-methyladenine, 5-hydroxymethylcytosine and N4-methylcytosine sites. MeDiCNet encodes nucleotide identity, extracts local patterns via a dynamic convolution module, captures global context through a Transformer encoder into which positional information is injected via rotary and clipped relative position embeddings, and adaptively fuses these feature streams through a gated fusion module for final classification. We evaluated MeDiCNet on seventeen benchmark datasets spanning bacteria, fungi, plants and mammals. Compared with other methods, MeDiCNet improved overall accuracy (ACC) by up to 8.1% and Matthews correlation coefficient (MCC) by up to 0.10. For example, it achieved 94.82% accuracy on the F. vesca 6mA dataset and the area under the ROC (AUC) curve above 0.98 on the Mus musculus 5hmC dataset. Crucially, rigorous analysis confirms that MeDiCNet recovers biologically authentic motifs with high fidelity in an unsupervised manner, while requiring only about 16% of the parameters of comparable large language models. These results demonstrate MeDiCNet's ability to capture complex local and global sequence features, providing a robust, efficient, and interpretable tool for large-scale, cross-type epigenomic analysis.</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148149773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"NphosNet: Predicting Protein N-Phosphorylation Sites via xLSTM and Enhanced PLM Features with a Weighted Three-Channel Cross-Attention Mechanism.","authors":"Lun Zhu, Yiyu Lin, Sen Yang","doi":"10.1007/s12539-026-00849-0","DOIUrl":"https://doi.org/10.1007/s12539-026-00849-0","url":null,"abstract":"<p><p>Protein phosphorylation, a pivotal post-translational modification mechanism, plays essential roles in cellular signaling and disease regulation. While O-phosphorylation has been extensively investigated, the biological significance of N-phosphorylation has only recently gained attention, with its study hindered by inherent challenges including site instability and detection limitations. To address these challenges, we present NphosNet, a deep learning framework with four technical innovations. First, we constructed a novel, class-imbalanced N-phosphorylation dataset comprising pH-913, pK-2060, and pR-1700 subsets. For comprehensive feature representation, we developed a hybrid embedding strategy combining amino acid tokenization with positional encoding, enhanced by ProtT5 and EMBER2 pre-trained model embeddings to capture deep semantic information from protein sequences. Architecturally, we introduced a three-branch framework integrating Transformer modules, optimized xLSTM blocks, CNN components, and spatial attention-enhanced ResNet units for multi-dimensional feature extraction. A novel weighted three-channel cross-attention mechanism was specifically designed for effective feature fusion across branches. Comparative evaluations demonstrate NphosNet's superior performance in N-phosphorylation site prediction (pH/pK/pR), achieving AUC values of 0.9227, 0.9099, and 0.9377 respectively, significantly outperforming existing methods. This advancement provides a robust computational tool for elucidating N-phosphorylation mechanisms in cellular processes and disease pathogenesis.</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148149806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"stGNN: Spatially Informed Cell-Type Deconvolution Based on Deep Graph Learning and Statistical Modeling.","authors":"Juntong Zhu, Daoyuan Wang, Siqi Chen, Lili Meng, Yahui Long, Cheng Liang","doi":"10.1007/s12539-025-00728-0","DOIUrl":"10.1007/s12539-025-00728-0","url":null,"abstract":"<p><p>Recent advancements in spatial transcriptomics (ST) technologies have greatly revolutionized our understanding of tissue heterogeneity and cellular functions. However, popular ST, such as 10x Visium, still fall short in achieving true single-cell resolution, underscoring an urgent need for in-silico methods that can accurately resolve cell type composition within ST data. While several methods have been proposed, most rely solely on gene expression profiles, often neglecting spatial context, which results in suboptimal performance. Additionally, many deconvolution methods dependent on scRNA-seq data fail to align the distribution of ST and scRNA-seq reference data, consequently affecting the accuracy of cell type mapping. In this study, we propose stGNN, a novel spatially-informed graph learning framework powered by statistical modeling for resolving fine-grained cell type compositions in ST. To capture comprehensive features, we develop a dual encoding module, utilizing both a graph convolutional network (GCN) and an auto-encoder to learn spatial and non-spatial representations respectively. Following that, we further design an adaptive attention mechanism to integrate these representations layer-by-layer, capturing multi-scale spatial structures from low to high order and thus improving representation learning. Additionally, for model training, we adopt a negative log-likelihood loss function that aligns the distribution of ST data with scRNA-seq (or snRNA-seq) reference data, enhancing the accuracy of cell type proportion prediction in ST. To assess the performance of stGNN, we applied our proposed model to six ST datasets from various platforms, including 10x Visium, Slide-seqV2, and Visium HD, for cell type proportion estimation. Our results demonstrate that stGNN consistently outperforms seven state-of-the-art methods. Notably, when applied to mouse brain tissues, stGNN successfully resolves clear cortical layers at a high resolution. Additionally, we show that stGNN is able to effectively resolve ST at different resolutions. In summary, stGNN provides a powerful framework for analyzing the spatial distribution of diverse cell populations in complex tissue structures. stGNN's code is openly shared on https://github.com/LiangSDNULab/stGNN .</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":"702-717"},"PeriodicalIF":3.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144505611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DynamicDTA: Drug-Target Binding Affinity Prediction Using Dynamic Descriptors and Graph Representation.","authors":"Dan Luo, Jinyu Zhou, Le Xu, Sisi Yuan, Xuan Lin","doi":"10.1007/s12539-025-00729-z","DOIUrl":"10.1007/s12539-025-00729-z","url":null,"abstract":"<p><strong>Motivation: </strong>Predicting drug-target binding affinity (DTA) is essential for identifying potential therapeutic candidates in drug discovery. However, most existing models rely heavily on static protein structures, often overlooking the dynamic nature of proteins, which is crucial for capturing conformational flexibility that will be beneficial for protein binding interactions.</p><p><strong>Methods: </strong>We introduce DynamicDTA, an innovative deep learning framework that incorporates static and dynamic protein features to enhance DTA prediction. The proposed DynamicDTA takes three types of inputs, including drug sequence, protein sequence, and dynamic descriptors. A molecular graph representation of the drug sequence is generated and subsequently processed through graph convolutional network, while the protein sequence is encoded using dilated convolutions. Dynamic descriptors, such as root mean square fluctuation, are processed through a multi-layer perceptron. These embedding features are fused with static protein features using cross-attention, and a tensor fusion network integrates all three modalities for DTA prediction.</p><p><strong>Results: </strong>Extensive experiments on three datasets demonstrate that DynamicDTA achieves by at least 3.4% improvement in <math><msub><mi>e</mi> <mtext>RMSE</mtext></msub> </math> score with comparison to seven state-of-the-art baseline methods. Additionally, predicting novel drugs for Human Immunodeficiency Virus Type 1 and visualizing the docking complexes further demonstrates the reliability and biological relevance of DynamicDTA.</p><p><strong>Availability and implementation: </strong>The source code is publicly available and can be accessed at https://github.com/shmily-ld/DynamicDTA .</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":"718-733"},"PeriodicalIF":3.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144247737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"scIMGCN: an Automatic Single-Cell Type Annotation Method Based on Interpretable Graph Convolutional Network.","authors":"Binhua Tang, Guowei Cheng, Xinyu Gao","doi":"10.1007/s12539-025-00738-y","DOIUrl":"10.1007/s12539-025-00738-y","url":null,"abstract":"<p><p>Rapid advancements in single-cell RNA sequencing (scRNA-seq) technology have significantly propelled research on cellular heterogeneity. However, the accurate identification and classification of cell types from large-scale single-cell datasets remains challenging. Graph convolutional networks (GCN) have gained popularity in single-cell analysis by effectively extracting features and annotating data using expression similarities and cell network structures, but the black-box nature hampers the interpretation of results, limiting their broader application. This study proposes scIMGCN, an innovative method for automated cell type annotation in single-cell datasets. This method incorporates advanced techniques to alleviate the constraints imposed by GCNs in practical contexts. First, graph structure representation is enhanced through network augmentation techniques, resulting in a 4.7% improvement in annotation accuracy. Second, an enhanced Transformer module addresses the issue of long-range dependencies in GCNs by dynamically modeling global relationships via its self-attention mechanism. This method removes the need for predefined graph structures, mitigates noise amplification, and achieves a 7.1% improvement in accuracy. Third, a GCN variant, based on the Kolmogorov-Arnold network (KAN), yielded improved feature representation and nonlinearity, achieving a 5.6% accuracy gain. Additionally, the model's decision transparency is enhanced by an interpretability masking mechanism. Experiments indicate scIMGCN attains accuracy between 94.8% and 100% across ten real datasets, exceeding traditional methods by more than 15%. Moreover, scIMGCN demonstrated a 4.8% improvement over existing state-of-the-art graph-based methods, thus highlighting its enhanced accuracy and scalability. Overall, scIMGCN demonstrated enhanced performance in cell-type annotation by effectively modeling complex long-range intercellular relationships, thus improving model interpretability and generalizability. The self-complied codes are available at https://github.com/gladex/scIMGCN .</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":"747-761"},"PeriodicalIF":3.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144667548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Relevance of 3D Rotationally Equivariant Neural Networks for Predicting Protein-Ligand Binding Affinities.","authors":"Gaili Li, Yongna Yuan, Ruisheng Zhang","doi":"10.1007/s12539-025-00745-z","DOIUrl":"10.1007/s12539-025-00745-z","url":null,"abstract":"<p><p>Proteins are fundamental to biological processes, mediating critical functions through precise molecular interactions. The rotational dynamics between ligand atoms and protein binding sites can significantly influence interaction efficacy by modifying spatial relationships. In our research, we present the PLAe (three-dimensional (3D) rotationally equivariant neural networks for predicting protein-ligand binding affinities) methodology. This novel model synergizes radial basis functions with e3nn networks to encapsulate the radial and angular dimensions of molecular features. Radial basis functions effectively measure interatomic distances, while e3nn-an advanced neural network utilizing spherical harmonics-maintains invariance under rotational and translational transformations. The Clebsch-Gordan coefficients are employed to integrate angular and atomic properties seamlessly. By merging radial basis and spherical harmonic elements with Clebsch-Gordan representations, our approach adeptly captures molecular rotational symmetries and interatomic interactions. The inclusion of an attention mechanism further refines the affinity predictions, ensuring a high level of precision. This integrative and sophisticated model sets a new benchmark to accurately predict protein-ligand binding affinities, leveraging intricate molecular details to enhance predictive performance.</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":"392-418"},"PeriodicalIF":3.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144855175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diffusion Model-Based Multi-Channel EEG Representation and Forecasting for Early Epileptic Seizure Warning.","authors":"Zekun Jiang, Wei Dai, Qu Wei, Ziyuan Qin, Rui Wei, Mianyang Li, Xiaolong Chen, Ying Huo, Jingyun Liu, Kang Li, Le Zhang","doi":"10.1007/s12539-025-00750-2","DOIUrl":"10.1007/s12539-025-00750-2","url":null,"abstract":"<p><p>Multi-channel electroencephalogram (EEG) signals are essentially spatio-temporal data collected from different regions of the brain. The representation and modeling of their spatio-temporal information are critical for EEG analysis, particularly in the diagnosis and assessment of neurological diseases such as epilepsy. Existing methods often rely on the representation of single-channel signals, overlooking the inherent spatio-temporal correlations within EEG data. Moreover, most deep learning-based EEG algorithms focus only on classifying and predicting the current signal states, with limited attention paid to forecasting the future development of EEG signals for early warning of disease events such as epileptic seizures. To address these limitations, we introduce EEG-DIF, a spatio-temporal representation and forecasting framework based on generative diffusion models. EEG-DIF reformulates the multi-channel signal forecasting task as a signal image completion problem and learns the temporal development relationships among arbitrary numbers of EEG channels through the processes of noise addition and recovery, enabling future trend generation and early warning based on multi-channel EEG data. Experimental results on the publicly available Siena Scalp EEG Database demonstrate that EEG-DIF can simultaneously predict the future dynamics of multi-channel EEG signals with a single model. The generated signals can be directly used for early seizure warning, achieving an average accuracy of 0.89. In summary, EEG-DIF provides a novel framework to represent spatio-temporal multi-channel biomedical signals, introduces an effective method for the early warning of epileptic seizures, and highlights the potential of generative models to optimize the clinical diagnostic workflows. The codes are available online at https://github.com/JZK00/EEG-DIF .</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":"628-639"},"PeriodicalIF":5.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144821314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}